Journal article · 2024 · Open access

Confidence in the Reasoning of Large Language Models

Yudi Pawitan, Chris C. Holmes

Harvard Data Science Review, 7(1) · Published 16 December 2024 · DOI 10.1162/99608f92.b033a087

Open PDFView at the publisherCite this paper

In brief

“Confidence in the Reasoning of Large Language Models” is a 2024 journal article by Yudi Pawitan and Chris C. Holmes, published in Harvard Data Science Review. OpenAlex counts 40 citations as of 20 November 2026, which puts it in the top 1% of works published in 2024 by citations. It is open access under a CC BY licence: the full text is free to read at Harvard Data Science Review.

Citations
40
Most cited in
2025 (21)
Field-weighted impact
3.30
References
22
Authors
2

Abstract

There is a growing literature on reasoning by large language models (LLMs), but the discussion on the uncertainty in their responses is still lacking. Our aim is to assess the extent of confidence that LLMs have in their answers and how it correlates with accuracy. Confidence is measured (i) qualitatively in terms of persistence in keeping their answer when prompted to reconsider, and (ii) quantitatively in terms of self-reported confidence score. We investigate the performance of three LLMs – GPT4o, GPT4-turbo, and Mistral—on two benchmark sets of questions on causal judgement and formal fallacies, and a set of probability and statistical puzzles and paradoxes. Although the LLMs show significantly better performance than random guessing, there is a wide variability in their tendency to change their initial answers. There is a positive correlation between qualitative confidence and accuracy, but the overall accuracy for the second answer is often worse than for the first answer. There is a strong tendency to overstate the self-reported confidence score. Confidence is only partially explained by the underlying token-level probability. The material effects of prompting on qualitative confidence and the strong tendency for overconfidence indicate that current LLMs do not have any internally coherent sense of confidence.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Pawitan, Y., & Holmes, C. C. (2024). Confidence in the Reasoning of Large Language Models. Harvard Data Science Review, 7(1). https://doi.org/10.1162/99608f92.b033a087

MLA 9

Pawitan, Yudi, and Chris C. Holmes. “Confidence in the Reasoning of Large Language Models.” Harvard Data Science Review, vol. 7, no. 1, 2024. https://doi.org/10.1162/99608f92.b033a087.

Chicago

Pawitan, Yudi and Chris C. Holmes. 2024. “Confidence in the Reasoning of Large Language Models.” Harvard Data Science Review 7 (1). https://doi.org/10.1162/99608f92.b033a087.

Harvard

Pawitan, Y. and Holmes, C. C. (2024) ‘Confidence in the Reasoning of Large Language Models’, Harvard Data Science Review, 7(1). doi:10.1162/99608f92.b033a087.

IEEE

Y. Pawitan and C. C. Holmes, “Confidence in the Reasoning of Large Language Models,” Harvard Data Science Review, vol. 7, no. 1, 2024, doi: 10.1162/99608f92.b033a087.

BibTeX

@article{pawitan2024confidence,
  title     = {{Confidence in the Reasoning of Large Language Models}},
  author    = {Pawitan, Yudi and Holmes, Chris C.},
  journal   = {Harvard Data Science Review},
  year      = {2024},
  volume    = {7},
  number    = {1},
  doi       = {10.1162/99608f92.b033a087},
  url       = {https://doi.org/10.1162/99608f92.b033a087}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling

  • large language models
  • uncertainty
  • overconfidence
  • self-reported confidence
  • causal judgment
  • probability puzzles
  • statistical paradoxes
  • prompting

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Pawitan, Y., & Holmes, C. C. (2024). Confidence in the Reasoning of Large Language Models. Harvard Data Science Review, 7(1). https://doi.org/10.1162/99608f92.b033a087

How many times has this paper been cited?

40 times, according to OpenAlex on 20 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at Harvard Data Science Review: sign in and open the PDF from this page.

Who wrote this paper?

Yudi Pawitan, Chris C. Holmes.

What is the DOI of this paper?

10.1162/99608f92.b033a087, permanently at https://doi.org/10.1162/99608f92.b033a087. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 20 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.